Deep learning applications in engineering: a systematic review

Abstract

Recent advances in deep learning algorithms and computing have resulted in tremendous gains in deep learning capabilities. Deep learning is currently able to achieve near-human level performance on a number of tasks. As a result, deep learning has been deployed in various real-life applications. There exists a growing body of literature devoted to further advancement of deep learning software and hardware implementations. In this paper, we conduct a systematic review of deep learning applications with emphasis on relevant applications in engineering. We highlight their strengths and recommend remedies regarding their weaknesses.